Music recommendation systems are an essential part of modern music streaming services, allowing for personalized discovery of music. However, two important challenges remain: the cold-start problem, where either new users or new songs have no interaction data, and the continuation problem, where the emotional context of a music listening session needs to be preserved while playing different songs with varying emotional affinities. This paper presents a quantum-assisted music recommendation system based on emotion intent recognition, multimodal feature fusion of audio, lyrics, and metadata, and quantum-assisted similarity computation using the Quantum k-Nearest Neighbors (QkNN) algorithm in combination with Grover’s search. Simulation experiments on the Qiskit simulator show that the quantum approach is highly effective in overcoming cold-start problems and identifying subtle overlaps in emotions more sensitively than cosine similarity. The Grover search also enhances the discovery of emotionally similar songs, thus improving the ranking resolution and recommendation refinement. The simulation results show high intra-list diversity (0.95) and novelty (0.84), indicating that the proposed system recommends relevant songs while encouraging discovery and avoiding repetitiveness and popularity bias.
C et al. (Mon,) studied this question.